Search pathology
Search pathology is a phenomenon best known from minimax search, where under
seemingly reasonable conditions, the deeper one searches, the worse he plays - the
opposite of what happens in practice. Similar behavior was observed in real-time
single-agent heuristic search. Search pathology was the subject of my Ph. D. thesis
under the supervision of Ivan Bratko and
Matjaž Gams. My research on the pathology
in single-agent search was done in collaboration with
Vadim Bulitko.
Publications
- Luštrek, M., Bratko, I, and Gams, M. (2012). Independent-valued minimax:
Pathological or beneficial?
Theoretical
Computer Science 422. [paper
in pdf] [link]
- Piltaver, R., Luštrek, M., and Gams, M. (2012). The pathology of heuristic
search in the 8-puzzle.
Journal of Experimental &
Theoretical Artificial Intelligence 24 (1). [paper
in pdf] [link]
- Nau, D. S., Luštrek, M., Parker, A., Bratko, I., and Gams, M. (2010). When
is it better not to look ahead?
Artificial
Intelligence 174 (16-17). [paper
in pdf] [link]
- Tavčar, A., Luštrek, M., and Gams, M. (2009). Patologija minimin preiskovanja.
Information Society conference. [paper
in pdf]
- Luštrek, M. (2008). Pathology in heuristic search.
AI Communications 21 (2-3). [paper
in pdf] [link]
- Gams, M., Luštrek, M., and Kaluža, B. (2008). Patologija končno razložena?
Information Society conference. [paper
in pdf]
- Luštrek, M., and Bulitko, V. (2008). Thinking too Much: Pathology in Pathfinding.
ECAI conference, short paper.
[paper
in pdf] [poster
in pdf] [slides
in ppt] [long
paper (unpublished) in pdf]
- Piltaver, R., Luštrek, M., and Gams, M. (2007). Search Pathology of 8-Puzzle.
Information Society conference. [paper
in pdf]
- Kaluža, B., Luštrek, M., and Gams, M. (2007). Patologija minimaksa v sintetičnih
drevesih in Pearlovi igri. Information Society conferencee.
[paper
in pdf]
- Luštrek, M., Gams, M., and Bratko, I. (2007). Zakaj preiskovati globlje?
Information Society conference. [paper
in pdf]
- Kaluža, B., Luštrek, M., Gams, M., and Tavčar, A. (2007). Pathology in minimax
searching. ERK conference. [paper
in pdf]
- Luštrek, M. (2007). Patologija v hevrističnih preiskovalnih algoritmih.
Ph. D. thesis, University of Ljubljana, Faculty
of Computer and Information Science. [thesis
in pdf] [slides
in ppt] [link]
- Bulitko, V., and Luštrek, M. (2006). Lookahead Pathology in Real-Time Path-Finding.
AAAI conference,
AAAI Member Abstracts and Posters [paper
in pdf] [poster
in pdf].
- Luštrek, M., and Bulitko, V. (2006). Lookahead Pathology in Real-Time Path-Finding.
AAAI conference,
Learning for Search workshop
[paper
in pdf] [poster
in pdf].
- Luštrek, M., Gams, M., and Bratko, I. (2006). Is Real-Valued Minimax Pathological?
Artificial Intelligence 170 (6-7). [paper
in pdf] [link]
- Luštrek, M. (2005). Pathology in Single-Agent Search.
Information Society conference. [paper
in pdf] [slides
in ppt]
- Luštrek, M., Bratko, I., and Gams, M. (2005). Why Minimax Works: An Alternative
Explanation. IJCAI conference. [paper
in pdf] [slides in ppt]
- Luštrek, M. (2004). Minimax Pathology and Real-Number Minimax Model.
ERK conference. [paper
in pdf] [slides
in ppt]
- Luštrek, M., and Gams, M. (2003). Minimaks in napaka pri ocenjevanju položajev.
Information Society conference. [paper
in pdf] [slides
in ppt]
Other documents
- Luštrek, M., and Bulitko, V. (2006). Lookahead Pathology in Real-Time pathfinding.
Presentation at the University of Alberta.
[slides
in ppt]
- Luštrek, M., Bratko, I., and Gams, M. (2005). Minimax Pathology. Second
presentation at the University of Alberta.
[slides in ppt]
- Luštrek, M., Bratko, I., and Gams, M. (2005). Minimax Pathology. First presentation
at the University of Alberta. [slides
in ppt]
- Luštrek, M., and Gams, M. (2004). Patologija minimaksa.
Solomon seminar 143. [slides
in ppt] [link]
I started working in this area as a postdoc at the
Institute for Biostatistics and Informatics
in Medicine and Ageing Research. I developed a machine-learning method for epitope
prediction based on peptide array data, which is relevant to vaccine design and
diagnostics. I was also involved in the research on pluripotency.
I am currently involved in the COVIRNA project,
which aims develop a diagniostic panel to predict outcomes of cardiovascualr
patients with COVID-19.
Publications
- Gomes, C. P. C., Ágg, B., Andova, A., Arslan, S., Baker, A., Barteková,
M., Beis, D., Betsou, F., Luštrek, M., et al., and Devaux, Y., on behalf of
the EU-CardioRNA COST Action (CA17129) (2019). Catalyzing transcriptomics
research in cardiovascular disease: The CardioRNA COST action CA17129.
Non-coding RNA Research 5 (2).
[paper
in pdf] [link]
- Gomes, C. P. C., Salgado-Somoza, A., Creemers, E. E., Creemers, D.,
Luštrek, M., and Devaux, Y., on behalf of the Cardiolinc network (2018).
Circular RNAs in the cardiovascular system.
Non-Coding RNA Research 3 (1).
[paper
in pdf] [link]
- Patro, R., Norel, R., Prill, R. J., Saez-Rodriguez, J., Lorenz, P., Steinbeck,
F., Ziems, B., Luštrek, M., Barbarini, N., Tiengo, A., Bellazzi, R., Thiesen,
H.-J., Stolovitzky, G., and Kingsford, C. (2016). A computational method for
designing diverse linear epitopes including citrullinated peptides with desired
binding affinities to intravenous immunoglobulin.
BMC Bioinformatics
17. [paper
in pdf] [link]
- Luštrek, M., Lorenz, P., Kreutzer, M., Qian, Z., Steinbeck, F., Wu, D.,
Born, N., Ziems, B., Hecker, M., Blank, M., Shoenfeld, Y., Cao, Z., Glocker,
M. O., Li, Y., Füllen, G., and Thiesen, H.-J. (2013). Epitope predictions indicate
the presence of two distinct types of epitope-antibody-reactivities determined
by epitope profiling of intravenous immunoglobulins. PLOS One. [paper
in pdf] [link]
- Scheubert, L., Luštrek, M., Schmidt, R., Repsilber, D., Füllen, G. (2012).
Tissue-based Alzheimer gene expression markers - comparison of multiple machine
learning approaches and investigation of redundancy in small biomarker sets.
BMC Bioinformatics 2012, 13. [paper
in pdf [link]
- Som, A, Luštrek, M., Kumar Singh, N., Füllen, G. (2012). Derivation of an
interaction/regulation network describing pluripotency in human. Gene 502 (2).
[paper
in pdf] [link]
- Luštrek, M. (2011). Strojno učenje epitopov iz peptidnih mikromrež.
Information Society conference. [paper
in pdf]
- Scheubert, L., Schmidt, R., Luštrek, M., Repsilber, D., and Füllen, G. (2011).
Searching for biomarkers of pluripotent stem cells.
GMDS conference, poster.
[link]
- Scheubert, L., Schmidt, R., Repsilber, D., Luštrek, M., and Füllen, G. (2011).
Learning biomarkers of pluripotent stem cells in mouse.
DNA Research 18 (4). [paper
in pdf] [link]
- Luštrek, M., Lorenz, P., Steinbeck, F., Füllen, G., and Thiesen, H.-J. (2010).
Epitope prediction based on peptide array data.
German Conference on Bioinformatics. [abstract
in pdf] [poster
in pdf]
Other documents
Tourism
We have developed an intelligent electronic tourist guide as a
web and mobile application. The guide prepares
a personalized itinerary for each user and then guides him on his trip. The personalization
relies on knowledge-based recommendations and collaborative filtering.
Publications
- Slapničar, G., Kaluža, B., Luštrek, M., and Bosnić, Z.
(2015). Recommender system as a service based on the Alternating Least
Squares algorithm. Information
Society conference. [paper
in pdf]
- Luštrek, M., Kaluža, B., Cvetković, B., and Gjoreski, H. (2013). E-turist:
Inteligentni elektronski turistični vodnik. Information
Society conference. [paper
in pdf] [slides
in pptx]
- Cvetković, B., Kaluža, B., Gjoreski, H., and Luštrek, M. (2013). Hybrid
recommender system for personalized POI selection.
Information Society conference. [paper
in pdf]
- Gjoreski, H., Cvetković, B., Kaluža, B., and Luštrek, M. (2013). Sightseeing
route planning. Information Society conference.
[paper in
pdf]
- Jurinčič, I., Gosar, A., Luštrek, M., Kaluža, B., Kerma, S., and Balažič,
G. (2013). E-tourist: Electronic mobile tourist guide.
Contemporary Trends in Tourism
and Hospitality conference. [paper
in pdf]
Games and search
Computer game playing was the subject of my B. Sc. thesis, for which I wrote a program for playing
tarok called
Silicon Tarokist. The program was substantially
improved afterwards. I later also collaborated with
Domen Marinčič, who worked on a Bayesian
decision model for bidding in tarok. I have also done some research on real-time single-agent heuristic search, where I
was investigating methods to determine the optimal lookahead depth. This research
is an offshoot of the research on search pathology and was also done in collaboration
with Vadim Bulitko.
Publications
- Bulitko, V., Luštrek, M., Schaeffer, J., Bjornsson, Y., and Sigmundarson,
S. (2008). Dynamic Control in Real-Time Heuristic Search.
Journal of Artificial Inteligence Research
32. [paper
in pdf] [link]
- Bulitko, V., Bjornsson, Y., Luštrek, M., Schaeffer, J., and Sigmundarson,
S. (2007). Dynamic Control in Path-Planning with Real-Time Heuristic Search.
ICAPS conference. [paper
in pdf] [poster
in pdf]
- Luštrek, M. (2006). Optimalna globina preiskovanja pri LRTA*.
Information Society conference. [paper
in pdf] [slides
in ppt]
- Marinčič, D., Gams, M., and Luštrek, M. (2006). Knowledge vs. Simulation
for Bidding in Tarok. Informatica 30
(3). [paper
in pdf]
- Luštrek, M., Gams, M., and Bratko, I. (2003). A Program for Playing Tarok.
ICGA Journal 26 (3). [paper
in pdf]
- Luštrek, M., and Gams, M. (2003). Intelligent System for Playing Tarok.
ITI conference,
CIT 11 (3). [paper
in pdf] [slides
in ppt]
- Luštrek, M. (2002). Računalniško igranje iger s kartami.
Information Society conference. [paper
in pdf] [slides
in ppt]
- Luštrek, M. (2002). Računalniško igranje iger s kartami. B. Sc. thesis,
University of Ljubljana, Faculty of Computer
and Information Science. [thesis
in pdf] [slides
in ppt]
Other documents
Machine learning
While I use machine learning in most of my research, I do not often research
machine learning itself. My main interest in this area is building classifiers
that are both comprehensible and accurate.
Publications
- Piltaver, R., Luštrek, M., Džeroski, S., Gjoreski, M., and Gams, M.
(2021). Learning comprehensible and accurate hybrid trees.
Expert
Systems
with Applications 164. [paper in pdf] [link]
- Piltaver, R., Luštrek, M., Gams, M., and Martinčić-Ipšić, S. (2016). What
makes classification trees comprehensible?
Expert Systems with Applications 62. [paper in pdf] [llink]
- Piltaver, R., Luštrek, M., Gams, M., and Martinčić-Ipšić, S. (2014). Comprehensibility
of classification trees - survey design validation.
ITIS conference. [paper
in pdf]
- Piltaver, R., Luštrek, M., Gams, M., and Martinčić-Ipšić, S. (2014). Comprehensibility
of classification trees - survey design. Information
Society conference. [paper
in pdf]
- Piltaver, R., Luštrek, M., and Gams, M. (2014) Multi-objective learning
of accurate and comprehensible classifiers - a case study.
ECAI conference,
STAIRS. [paper
in pdf] [poster
in pdf]
- Piltaver, R., Luštrek, M., Zupančič, J., Džeroski, S., and Gams, M. (2014).
Multi-objective learning of hybrid classifiers.
ECAI conference. [paper
in pdf]
- Luštrek, M. (2004). Luščenje podatkov s skritimi markovskimi modeli.
Information Society conference. [paper
in pdf] [slides
in ppt]
Genre classification
The ability to classify web pages into genres can be a helpful addition to a
search engine. We developed machine learning methods for genre classification in
Alvis EU FP6 project, but the development
continues after the end of the project. I collaborate on this with
Vedrana Vidulin.
The web genre dataset
used in our research
Publications
- Vidulin, V., Luštrek, M., and Gams, M. (2009). Multi-Label Approaches to
Web Genre Identification. Journal for Language
Technology and Computational Linguistics. [paper
in pdf]
- Vidulin, V., Luštrek, M., and Gams, M. (2007). Using Genres to Improve Search
Engines. RANLP conference,
Towards
Genre-Enabled Search Engines: The Impact of NLP workshop. [paper
in pdf]
- Vidulin, V., Luštrek, M., and Gams, M. (2007). Evaluation of different approaches
to training a genre classifier. AIPR
workshop. [paper
in pdf]
- Vidulin, V., Luštrek, M., and Gams, M. (2007). Training the Genre Classifier
for Automatic Classification of Web Pages. ITI
conference, CIT 15 (4). [paper
in pdf]
- Vidulin, V., Luštrek, M., and Gams, M. (2006). Comparison of the Performance
of Genre Classifiers Trained by Different Machine Learning Algorithms.
Information Society conference. [paper
in pdf]
- Pivk, A., Gams, M., Luštrek, M. (2006). Semantic Search in Tabular Structures.
Informatica 30 (2). [paper
in pdf]
Other documents
- Luštrek, M. (2007). Overview of Automatic Genre Identification. Technical
Report IJS-DP-9735. [report
in pdf]
Other
Occasionally I also dabble in other areas.
Publications
- Strojnik, L., Stopar, M., Zlatić, E., Ženko, B., Žnidaršič, M., Bohanec,
M., Mileva Boshkoska, B., Luštrek, M., Gradišek, A., et al., and Ogrinc, N.
(2019). Authentication of key aroma compounds in apple using stable isotope
approach. Food Chemistry 277.
[paper
in pdf] [link]
- Strojnik, L., Stopar, M., Koron, D., Ženko, B., Žnidaršič, M., Bohanec,
M., Mileva Boshkoska, B., Luštrek, M., Gradišek, A., et al., and Ogrinc, N.
(2018). Compound-specific stable isotope analysis as a solution for
differentiation between natural and synthetic aroma compounds. Isotope Ratio
MS Day.
- Strojnik, L., Stopar, M., Koron, D., Ženko, B., Žnidaršič, M., Bohanec,
M., Mileva Boshkoska, B., Luštrek, M., Gradišek, A., et al, and Ogrinc, N.
(2018). Authentification of apple and strawberry key aroma compounds using
stable isotope approach. Workshop on Mass spectrometry in support of the
environment, food, and health interaction and disease.
- Luštrek, M., Bohanec, M., Mileva Boshkoska, B., Cigale, M., Gradišek,
A., Strojnik, L., Ženko, B., Žnidaršič, M., and Ogrinc, N. (2018).
Inteligentne računalniške metode za ugotavljanje pristnosti in drugih
lastnosti arom. Veliki spomladanski živilski seminar SRIP HRANA. [abstract
in pdf]
- Strojnik, L., Stopar, M., Koron, D., Ženko, B., Žnidaršič, M., Bohanec,
M., Mileva Boshkoska, B., Luštrek, M., Gradišek, A., et al., and Ogrinc, N.
(2018). Characterization of Slovenian apple and strawberry aromas for
authenticity assessment using stable isotope approach.
IPSSC conference.
[abstract in pdf]
- Gradišek, A., Slapničar, G., Šorn, J., Luštrek, M., Gams, M., and Grad,
J. (2017). Predicting species identity of bumblebees through analysis of flight
buzzing sounds. Bioacoustics 26
(1). [paper in pdf] [link]
- Gradišek, A., Budna, B., Gjoreski, M., Luštrek, M., and Gams, M. (2017).
JSI sound: A machine-learning tool in Orange for classification of diverse
biosounds. International Bioacoustics Congress.
- Gradišek, A., Slapničar, G., Šorn, J., Kaluža, B., Luštrek, M., Gams,
M., Hui, H., Trilar, T., and Grad, J. (2015). How to recognize animal
species based on sound - a case study on bumblebees, birds, and frogs. Information
Society conference. [paper
in pdf]
- Černe, M., Kaluža, B., and Luštrek, M. (2014). Analiza nakupov in modeliranje
pospeševanja prodaje v spletni trgovini. Information
Society conference. [paper
in pdf]
- Yusupov, M., Luštrek, M., Grad, J., and Gams, M. (2014). Recognition of
bumblebee species by their buzzing sound. Information
Society conference. [paper
in pdf] [slides
in pptx]
- Gams, M., Horvat, M., Ožek, M., Luštrek, M., and Gradišek, A. (2014). Integrating
artificial and human intelligence into tablet production process.
AAPS PharmSciTeche. [paper
in pdf] [link]
- Mirčevska, V., Luštrek, M., Bežek, A., Gams, M. (2014). Discovering strategic
behaviour of multi-agent systems in adversary settings.
Computing and informatics
33 (1). [paper
in pdf]